SiteCheck Agent Intel & Dev

Compares a public page now with its earliest Internet

agent_intel_live_page_diff

Read-only

Compares a public page now with its earliest Internet Archive (Wayback) snapshot on or after a date: changed yes/no, word similarity, added and removed text lines, and the price-like amounts ($, €, £) before and after. Only what the archive captured is compared; pages the archive never saved return 404. Price: $0.002 in USDC per successful call, paid with x402 (Base, Solana or Arc); failed calls are not charged.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "agent_intel_live_page_diff"
  }
}

Input Schema

Name	Required	Description	Default
`url`	Yes	Public http(s) page address
`since`	No	Baseline date YYYY-MM-DD (default: 30 days ago)

Output Schema

Name	Required	Description	Default
`url`	No
`added`	No
`source`	No
`changed`	No
`removed`	No
`baseline`	No
`checkedAt`	No
`addedCount`	No
`similarity`	No
`pricesAfter`	No
`pricesBefore`	No
`removedCount`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.2/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavior beyond that: the exact comparison output shape, the 404 failure mode for unarchived pages, and a full cost model ($0.002 USDC per successful call via x402 on Base, Solana or Arc, with failed calls not charged). Cost and failure semantics are the details an agent most needs before invoking a paid tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with what the tool does and what it returns, followed by the coverage caveat and then pricing. The pricing sentence is long but every clause (currency, protocol, chains, no-charge-on-failure) carries decision-relevant information; no filler is present.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present the description need not document return values, yet it still summarizes them, and it covers the two things structured fields cannot: archive-coverage failure behavior and payment terms. For a two-parameter read-only tool this is everything an agent needs to decide and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are documented, so the schema already carries the load. The description adds one nuance beyond the schema — that the snapshot chosen is the earliest one 'on or after' the baseline date, resolving inclusive-boundary ambiguity — but says nothing further about the url parameter or date edge cases.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (compares), resource (public page vs. earliest Wayback snapshot), and names the concrete outputs: changed yes/no, word similarity, added/removed lines, and price-like amounts. An agent can distinguish this from siblings like html_dom_to_clean_markdown or reader_markdown_extract, which read the current page but have no temporal baseline.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the use case (detecting change on a page since a date) and gives a hard precondition: 'Only what the archive captured is compared; pages the archive never saved return 404.' However, it never names an alternative tool or an explicit when-not condition, so routing between this and the page-extraction siblings is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All SiteCheck Agent Intel & Dev tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?